Simple Inner Join on 2 tables resulting in wrong estimated rows and slow performance

I'm having trouble understanding why a seemingly simple query which does an inner join on 2 tables is resulting in an estimated row count of 1, when the actual is almost 2 million. I don't see any issues with missing indexes, and 98% of the cost of query is happening as an index seek. I don't see any I/O or CPU red flags when they query runs, which takes about 12 seconds. Adding statistics doesn't seem to make sense here since the query is simply joining on ids, and both tables have clustered indexes on those ids as primary keys.I'm having trouble understanding why a seemingl